Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307642420> ?p ?o ?g. }
- W4307642420 endingPage "15" @default.
- W4307642420 startingPage "1" @default.
- W4307642420 abstract "In recent years, biometric recognition patterns have attracted the attention of many researchers, among which human ears, as a unique and stable biometric feature, have significant advantages in verifying personal identity. In the Internet era, a system with low computing cost and good real-time performance is more popular. Most of the existing ear recognition methods are based on a large parameter network model, which causes a large memory footprint and computational overhead. This paper proposes an efficient and lightweight human ear recognition method (ELERNet) based on MobileNet V2. Based on the MobileNet V2 model, dynamic convolution decomposition is introduced to enhance the representation ability of human ear features. Then, combined with the coordinate attention mechanism, the spatial features of human ear images are aggregated to locate the location information of the human ear features more accurately. We conducted experiments on AWE and EarVN1.0 human ear datasets. Compared with the MobileNet V2 model, the recognition accuracy of our method is significantly improved. Using less computing hardware resources, the ELERNet model achieves 83.52% and 96.10% Rank-1 (R1) recognition accuracy, respectively, which is better than other models. Finally, we provide a visual interpretation using GradCAM technology, and the results show that our method can learn specific and discriminative features in the ear images." @default.
- W4307642420 created "2022-11-04" @default.
- W4307642420 creator A5015488490 @default.
- W4307642420 creator A5033049363 @default.
- W4307642420 creator A5079879829 @default.
- W4307642420 creator A5087702678 @default.
- W4307642420 date "2022-10-30" @default.
- W4307642420 modified "2023-10-14" @default.
- W4307642420 title "An Efficient and Lightweight Method for Human Ear Recognition Based on MobileNet" @default.
- W4307642420 cites W1996808886 @default.
- W4307642420 cites W2018953191 @default.
- W4307642420 cites W2032962413 @default.
- W4307642420 cites W2098747085 @default.
- W4307642420 cites W2153979357 @default.
- W4307642420 cites W2551082533 @default.
- W4307642420 cites W2792027052 @default.
- W4307642420 cites W2792583777 @default.
- W4307642420 cites W2794657927 @default.
- W4307642420 cites W2798101467 @default.
- W4307642420 cites W2804800999 @default.
- W4307642420 cites W2888744770 @default.
- W4307642420 cites W2895160458 @default.
- W4307642420 cites W2903961886 @default.
- W4307642420 cites W2924068127 @default.
- W4307642420 cites W2957014022 @default.
- W4307642420 cites W2964247301 @default.
- W4307642420 cites W2966281161 @default.
- W4307642420 cites W2974287252 @default.
- W4307642420 cites W2979492580 @default.
- W4307642420 cites W2981102178 @default.
- W4307642420 cites W3031060177 @default.
- W4307642420 cites W3033847194 @default.
- W4307642420 cites W3034284131 @default.
- W4307642420 cites W3077340104 @default.
- W4307642420 cites W3081836667 @default.
- W4307642420 cites W3082520800 @default.
- W4307642420 cites W3086084680 @default.
- W4307642420 cites W3088580052 @default.
- W4307642420 cites W3106912766 @default.
- W4307642420 cites W3108940191 @default.
- W4307642420 cites W3118802361 @default.
- W4307642420 cites W3124136285 @default.
- W4307642420 cites W3129376202 @default.
- W4307642420 cites W3137043462 @default.
- W4307642420 cites W3154738895 @default.
- W4307642420 cites W3160659438 @default.
- W4307642420 cites W3161649047 @default.
- W4307642420 cites W3186345593 @default.
- W4307642420 cites W3188277880 @default.
- W4307642420 cites W3191781005 @default.
- W4307642420 cites W3196859148 @default.
- W4307642420 cites W4206064635 @default.
- W4307642420 cites W4213453433 @default.
- W4307642420 cites W4214805610 @default.
- W4307642420 cites W4220659807 @default.
- W4307642420 cites W4226196074 @default.
- W4307642420 cites W4243492817 @default.
- W4307642420 cites W4283070653 @default.
- W4307642420 cites W4285248638 @default.
- W4307642420 cites W4286681770 @default.
- W4307642420 doi "https://doi.org/10.1155/2022/9069007" @default.
- W4307642420 hasPublicationYear "2022" @default.
- W4307642420 type Work @default.
- W4307642420 citedByCount "3" @default.
- W4307642420 countsByYear W43076424202023 @default.
- W4307642420 crossrefType "journal-article" @default.
- W4307642420 hasAuthorship W4307642420A5015488490 @default.
- W4307642420 hasAuthorship W4307642420A5033049363 @default.
- W4307642420 hasAuthorship W4307642420A5079879829 @default.
- W4307642420 hasAuthorship W4307642420A5087702678 @default.
- W4307642420 hasBestOaLocation W43076424201 @default.
- W4307642420 hasConcept C111919701 @default.
- W4307642420 hasConcept C112356035 @default.
- W4307642420 hasConcept C121332964 @default.
- W4307642420 hasConcept C132943942 @default.
- W4307642420 hasConcept C138885662 @default.
- W4307642420 hasConcept C151730666 @default.
- W4307642420 hasConcept C153180895 @default.
- W4307642420 hasConcept C154945302 @default.
- W4307642420 hasConcept C184297639 @default.
- W4307642420 hasConcept C24890656 @default.
- W4307642420 hasConcept C2776401178 @default.
- W4307642420 hasConcept C2779960059 @default.
- W4307642420 hasConcept C28490314 @default.
- W4307642420 hasConcept C2992441837 @default.
- W4307642420 hasConcept C41008148 @default.
- W4307642420 hasConcept C41895202 @default.
- W4307642420 hasConcept C45347329 @default.
- W4307642420 hasConcept C50644808 @default.
- W4307642420 hasConcept C86803240 @default.
- W4307642420 hasConcept C97931131 @default.
- W4307642420 hasConceptScore W4307642420C111919701 @default.
- W4307642420 hasConceptScore W4307642420C112356035 @default.
- W4307642420 hasConceptScore W4307642420C121332964 @default.
- W4307642420 hasConceptScore W4307642420C132943942 @default.
- W4307642420 hasConceptScore W4307642420C138885662 @default.
- W4307642420 hasConceptScore W4307642420C151730666 @default.
- W4307642420 hasConceptScore W4307642420C153180895 @default.